# Supermemory — MCP server on mcp.ai
> Connect your Supermemory account and use 11 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Supermemory is a memory and context API for ingesting, organizing, searching, and recalling information across applications.

By: mcp.ai · official
Page: https://mcp.ai/supermemory

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_supermemory?ms=1787293740000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/supermemory/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/supermemory/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/supermemory/skill.md
Postman collection (v2.1): https://mcp.ai/supermemory/postman.json

## Tools
- supermemory_add_document(content: string, dreaming?: string, metadata?: object, custom_id?: string, task_type?: string, container_tag?: string, entity_context?: string, filter_by_metadata?: object) — Ingest text or a public URL as a Supermemory document and return its document ID and initial processing status.
- supermemory_add_documents(dreaming?: string, documents: object[]) — Add 1 to 600 documents in one request, with explicit per-document metadata and processing options. HTTP 200 may contain partial failures; callers must inspect failed, success, and every result rather 
- supermemory_delete_document(document_id: string) — Permanently delete one document by ID. This does not remove the document's container-tag settings record.
- supermemory_get_account_status() — Return the connected Supermemory organization's plan, credit balance, high-level usage, and reset date.
- supermemory_get_document(document_id: string) — Get one document's content, metadata, source details, and processing status by document ID.
- supermemory_get_document_chunks(document_id: string) — Return the ordered extracted chunks for one processed document.
- supermemory_get_profile(query?: string, buckets?: string[], filters?: object, include?: string[], threshold?: number, container_tag: string) — Retrieve the static, dynamic, or bucketed profile learned for one container tag, optionally with matching search results.
- supermemory_list_documents(sort?: string, limit?: integer, order?: string, filters?: object, filepath?: string, next_cursor?: string, container_tags?: string[], include_content?: boolean) — List documents, optionally filtered by containers, metadata, or filepath, one page at a time.
- supermemory_list_memories(sort?: string, limit?: integer, order?: string, filters?: object, next_cursor?: string, container_tags: string[]) — List extracted memory entries for one or more container tags, one page at a time.
- supermemory_search_context(limit?: integer, query: string, rerank?: boolean, filters?: object, include?: object, aggregate?: boolean, threshold?: number, search_mode?: string, rewrite_query?: boolean, container_tags?: string[]) — Semantically search Supermemory memories, document chunks, or both, with optional container and metadata filters.
- supermemory_update_document(content?: string, metadata?: object, custom_id?: string, task_type?: string, document_id: string, container_tag?: string, filter_by_metadata?: object) — Update the content, metadata, container, or processing configuration of one existing document. When metadata is supplied, it completely replaces the document's metadata, so omitted metadata keys are r

## Example prompts
- "What can I do in Supermemory?"
- "Show me a summary of my Supermemory account"

## Links
Docs: https://mcp.ai/docs/mcps/supermemory
Website: https://mcp.ai/mcps/supermemory